Instructions to use quarterturn/wan2.2-14b-t2v-bbwhot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use quarterturn/wan2.2-14b-t2v-bbwhot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-T2V-14B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("quarterturn/wan2.2-14b-t2v-bbwhot") prompt = "A man with short gray hair plays a red electric guitar." output = pipe(prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
NOTE NOTE NOTE!!!! DO NOT USE I made a mistake in training the low-noise LoRA, accidentally using the high noise timesteps in the low noise settings. BAD! WRONG! BAD DOG! NO!
I will correct it soon, stay tuned.
A Wan 2.2 14B t2v LoRA for creating BBW (Big Beautiful Women) Same dataset as the 2.1 LoRA. High and low noise versions available.
Trained on 147 images to epoch 80 rank 64.
- Downloads last month
- -